from aitlas.datasets import (
AIDDataset,
EurosatDataset,
PatternNetDataset,
Resisc45Dataset,
RSD46WHUDataset,
RSICB256Dataset,
RSSCN7Dataset,
SAT6Dataset,
SiriWhuDataset,
UcMercedDataset,
WHURS19Dataset,
CLRSDataset
)
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/AID",
"csv_file_path": "/media/hdd/multi-class/AID/train.csv"
}
train_dataset = AIDDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 10000
| Label | Count | |
|---|---|---|
| 0 | Airport | 360 |
| 1 | BareLand | 310 |
| 2 | BaseballField | 220 |
| 3 | Beach | 400 |
| 4 | Bridge | 360 |
| 5 | Center | 260 |
| 6 | Church | 240 |
| 7 | Commercial | 350 |
| 8 | DenseResidential | 410 |
| 9 | Desert | 300 |
| 10 | Farmland | 370 |
| 11 | Forest | 250 |
| 12 | Industrial | 390 |
| 13 | Meadow | 280 |
| 14 | MediumResidential | 290 |
| 15 | Mountain | 340 |
| 16 | Park | 350 |
| 17 | Parking | 390 |
| 18 | Playground | 370 |
| 19 | Pond | 420 |
| 20 | Port | 380 |
| 21 | RailwayStation | 260 |
| 22 | Resort | 290 |
| 23 | River | 410 |
| 24 | School | 300 |
| 25 | SparseResidential | 300 |
| 26 | Square | 330 |
| 27 | Stadium | 290 |
| 28 | StorageTanks | 360 |
| 29 | Viaduct | 420 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/EuroSAT",
"csv_file_path": "/media/hdd/multi-class/EuroSAT/train.csv"
}
train_dataset = EurosatDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 27000
| Label | Count | |
|---|---|---|
| 0 | AnnualCrop | 3000 |
| 1 | Forest | 3000 |
| 2 | HerbaceousVegetation | 3000 |
| 3 | Highway | 2500 |
| 4 | Industrial | 2500 |
| 5 | Pasture | 2000 |
| 6 | PermanentCrop | 2500 |
| 7 | Residential | 3000 |
| 8 | River | 2500 |
| 9 | SeaLake | 3000 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/PatternNet",
"csv_file_path": "/media/hdd/multi-class/PatternNet/train.csv"
}
train_dataset = PatternNetDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 30400
| Label | Count | |
|---|---|---|
| 0 | airplane | 800 |
| 1 | baseball_field | 800 |
| 2 | basketball_court | 800 |
| 3 | beach | 800 |
| 4 | bridge | 800 |
| 5 | cemetery | 800 |
| 6 | chaparral | 800 |
| 7 | christmas_tree_farm | 800 |
| 8 | closed_road | 800 |
| 9 | coastal_mansion | 800 |
| 10 | crosswalk | 800 |
| 11 | dense_residential | 800 |
| 12 | ferry_terminal | 800 |
| 13 | football_field | 800 |
| 14 | forest | 800 |
| 15 | freeway | 800 |
| 16 | golf_course | 800 |
| 17 | harbor | 800 |
| 18 | intersection | 800 |
| 19 | mobile_home_park | 800 |
| 20 | nursing_home | 800 |
| 21 | oil_gas_field | 800 |
| 22 | oil_well | 800 |
| 23 | overpass | 800 |
| 24 | parking_lot | 800 |
| 25 | parking_space | 800 |
| 26 | railway | 800 |
| 27 | river | 800 |
| 28 | runway | 800 |
| 29 | runway_marking | 800 |
| 30 | shipping_yard | 800 |
| 31 | solar_panel | 800 |
| 32 | sparse_residential | 800 |
| 33 | storage_tank | 800 |
| 34 | swimming_pool | 800 |
| 35 | tennis_court | 800 |
| 36 | transformer_station | 800 |
| 37 | wastewater_treatment_plant | 800 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/RESISC45",
"csv_file_path": "/media/hdd/multi-class/RESISC45/train.csv"
}
train_dataset = Resisc45Dataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 31500
| Label | Count | |
|---|---|---|
| 0 | airplane | 700 |
| 1 | airport | 700 |
| 2 | baseball_diamond | 700 |
| 3 | basketball_court | 700 |
| 4 | beach | 700 |
| 5 | bridge | 700 |
| 6 | chaparral | 700 |
| 7 | church | 700 |
| 8 | circular_farmland | 700 |
| 9 | cloud | 700 |
| 10 | commercial_area | 700 |
| 11 | dense_residential | 700 |
| 12 | desert | 700 |
| 13 | forest | 700 |
| 14 | freeway | 700 |
| 15 | golf_course | 700 |
| 16 | ground_track_field | 700 |
| 17 | harbor | 700 |
| 18 | industrial_area | 700 |
| 19 | intersection | 700 |
| 20 | island | 700 |
| 21 | lake | 700 |
| 22 | meadow | 700 |
| 23 | medium_residential | 700 |
| 24 | mobile_home_park | 700 |
| 25 | mountain | 700 |
| 26 | overpass | 700 |
| 27 | palace | 700 |
| 28 | parking_lot | 700 |
| 29 | railway | 700 |
| 30 | railway_station | 700 |
| 31 | rectangular_farmland | 700 |
| 32 | river | 700 |
| 33 | roundabout | 700 |
| 34 | runway | 700 |
| 35 | sea_ice | 700 |
| 36 | ship | 700 |
| 37 | snowberg | 700 |
| 38 | sparse_residential | 700 |
| 39 | stadium | 700 |
| 40 | storage_tank | 700 |
| 41 | tennis_court | 700 |
| 42 | terrace | 700 |
| 43 | thermal_power_station | 700 |
| 44 | wetland | 700 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/RSD46-WHU/train",
"csv_file_path": "/media/hdd/multi-class/RSD46-WHU/train/train.csv"
}
train_dataset = RSD46WHUDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 99381
| Label | Count | |
|---|---|---|
| 0 | Airplane | 2575 |
| 1 | Airport | 1405 |
| 2 | Artificial dense forest land | 2388 |
| 3 | Artificial sparse forest land | 2404 |
| 4 | Bare land | 851 |
| 5 | Basketball court | 2534 |
| 6 | Blue structured factory building | 2611 |
| 7 | Building | 2940 |
| 8 | Construction site | 2786 |
| 9 | Cross river bridge | 1910 |
| 10 | Crossroads | 1741 |
| 11 | Dense tall building | 2608 |
| 12 | Dock | 2675 |
| 13 | Fish pond | 1372 |
| 14 | Footbridge | 2230 |
| 15 | Graff | 2559 |
| 16 | Grassland | 2408 |
| 17 | Low scattered building | 2039 |
| 18 | Lrregular farmland | 2665 |
| 19 | Medium density scattered building | 894 |
| 20 | Medium density structured building | 3015 |
| 21 | Natural dense forest land | 2550 |
| 22 | Natural sparse forest land | 2519 |
| 23 | Oiltank | 1368 |
| 24 | Overpass | 2128 |
| 25 | Parking lot | 2598 |
| 26 | Plasticgreenhouse | 863 |
| 27 | Playground | 2728 |
| 28 | Railway | 2646 |
| 29 | Red structured factory building | 2536 |
| 30 | Refinery | 2259 |
| 31 | Regular farmland | 2728 |
| 32 | Scattered blue roof factory building | 2593 |
| 33 | Scattered red roof factory building | 2497 |
| 34 | Sewage plant-type-one | 458 |
| 35 | Sewage plant-type-two | 364 |
| 36 | Ship | 2563 |
| 37 | Solar power station | 2579 |
| 38 | Sparse residential area | 2534 |
| 39 | Square | 2813 |
| 40 | Steelsmelter | 2494 |
| 41 | Storage land | 1798 |
| 42 | Tennis court | 1322 |
| 43 | Thermal power plant | 1074 |
| 44 | Vegetable plot | 2452 |
| 45 | Water | 2307 |
test_dataset_config = {
"dir_path": "/media/hdd/multi-class/RSD46-WHU/val",
"csv_file_path": "/media/hdd/multi-class/RSD46-WHU/val/train.csv"
}
test_dataset = RSD46WHUDataset(test_dataset_config)
print(f"Total number of images: {len(test_dataset)}")
fig = test_dataset.show_batch(15)
fig = test_dataset.data_distribution_barchart()
test_dataset.data_distribution_table()
Total number of images: 17512
| Label | Count | |
|---|---|---|
| 0 | Airplane | 454 |
| 1 | Airport | 247 |
| 2 | Artificial dense forest land | 420 |
| 3 | Artificial sparse forest land | 424 |
| 4 | Bare land | 150 |
| 5 | Basketball court | 447 |
| 6 | Blue structured factory building | 460 |
| 7 | Building | 518 |
| 8 | Construction site | 491 |
| 9 | Cross river bridge | 337 |
| 10 | Crossroads | 307 |
| 11 | Dense tall building | 460 |
| 12 | Dock | 472 |
| 13 | Fish pond | 241 |
| 14 | Footbridge | 393 |
| 15 | Graff | 451 |
| 16 | Grassland | 424 |
| 17 | Low scattered building | 359 |
| 18 | Lrregular farmland | 470 |
| 19 | Medium density scattered building | 157 |
| 20 | Medium density structured building | 532 |
| 21 | Natural dense forest land | 450 |
| 22 | Natural sparse forest land | 445 |
| 23 | Oiltank | 241 |
| 24 | Overpass | 375 |
| 25 | Parking lot | 458 |
| 26 | Plasticgreenhouse | 152 |
| 27 | Playground | 481 |
| 28 | Railway | 466 |
| 29 | Red structured factory building | 447 |
| 30 | Refinery | 399 |
| 31 | Regular farmland | 481 |
| 32 | Scattered blue roof factory building | 457 |
| 33 | Scattered red roof factory building | 440 |
| 34 | Sewage plant-type-one | 80 |
| 35 | Sewage plant-type-two | 64 |
| 36 | Ship | 451 |
| 37 | Solar power station | 454 |
| 38 | Sparse residential area | 447 |
| 39 | Square | 496 |
| 40 | Steelsmelter | 439 |
| 41 | Storage land | 316 |
| 42 | Tennis court | 232 |
| 43 | Thermal power plant | 189 |
| 44 | Vegetable plot | 432 |
| 45 | Water | 406 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/RSI-CB256",
"csv_file_path": "/media/hdd/multi-class/RSI-CB256/train.csv"
}
train_dataset = RSICB256Dataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 24747
| Label | Count | |
|---|---|---|
| 0 | airplane | 351 |
| 1 | airport_runway | 678 |
| 2 | artificial_grassland | 283 |
| 3 | avenue | 544 |
| 4 | bare_land | 864 |
| 5 | bridge | 469 |
| 6 | city_building | 1014 |
| 7 | coastline | 459 |
| 8 | container | 660 |
| 9 | crossroads | 553 |
| 10 | dam | 324 |
| 11 | desert | 1092 |
| 12 | dry_farm | 1309 |
| 13 | forest | 1082 |
| 14 | green_farmland | 644 |
| 15 | highway | 223 |
| 16 | hirst | 628 |
| 17 | lakeshore | 438 |
| 18 | mangrove | 1049 |
| 19 | marina | 366 |
| 20 | mountain | 812 |
| 21 | parkinglot | 467 |
| 22 | pipeline | 198 |
| 23 | residents | 810 |
| 24 | river | 539 |
| 25 | river_protection_forest | 524 |
| 26 | sandbeach | 536 |
| 27 | sapling | 879 |
| 28 | sea | 1028 |
| 29 | shrubwood | 1331 |
| 30 | snow_mountain | 1153 |
| 31 | sparse_forest | 1110 |
| 32 | storage_room | 1307 |
| 33 | stream | 688 |
| 34 | town | 335 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/RSSCN7",
"csv_file_path": "/media/hdd/multi-class/RSSCN7/train.csv"
}
train_dataset = RSSCN7Dataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 2800
| Label | Count | |
|---|---|---|
| 0 | farm_land | 400 |
| 1 | forest | 400 |
| 2 | grass_land | 400 |
| 3 | industrial_region | 400 |
| 4 | parking_lot | 400 |
| 5 | residential_region | 400 |
| 6 | river_lake | 400 |
train_dataset_config = {
"mat_file_path": "/media/hdd/multi-class/SAT/sat-6-full.mat",
"mode": "train"
}
train_dataset = SAT6Dataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 324000
| Label | Count | |
|---|---|---|
| 0 | barren land | 14923 |
| 1 | buildings | 8192 |
| 2 | grassland | 56809 |
| 3 | roads | 50347 |
| 4 | trees | 73397 |
| 5 | water bodies | 120332 |
test_dataset_config = {
"mat_file_path": "/media/hdd/multi-class/SAT/sat-6-full.mat",
"mode": "test"
}
test_dataset = SAT6Dataset(test_dataset_config)
print(f"Total number of images: {len(test_dataset)}")
fig = test_dataset.show_batch(15)
fig = test_dataset.data_distribution_barchart()
test_dataset.data_distribution_table()
Total number of images: 81000
| Label | Count | |
|---|---|---|
| 0 | barren land | 3714 |
| 1 | buildings | 2070 |
| 2 | grassland | 14185 |
| 3 | roads | 12596 |
| 4 | trees | 18367 |
| 5 | water bodies | 30068 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/SIRI-WHU",
"csv_file_path": "/media/hdd/multi-class/SIRI-WHU/train.csv"
}
train_dataset = SiriWhuDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 2400
| Label | Count | |
|---|---|---|
| 0 | agriculture | 200 |
| 1 | commercial | 200 |
| 2 | harbor | 200 |
| 3 | idle_land | 200 |
| 4 | industrial | 200 |
| 5 | meadow | 200 |
| 6 | overpass | 200 |
| 7 | park | 200 |
| 8 | pond | 200 |
| 9 | residential | 200 |
| 10 | river | 200 |
| 11 | water | 200 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/UCMerced",
"csv_file_path": "/media/hdd/multi-class/UCMerced/train.csv"
}
train_dataset = UcMercedDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 2100
| Label | Count | |
|---|---|---|
| 0 | agricultural | 100 |
| 1 | airplane | 100 |
| 2 | baseballdiamond | 100 |
| 3 | beach | 100 |
| 4 | buildings | 100 |
| 5 | chaparral | 100 |
| 6 | denseresidential | 100 |
| 7 | forest | 100 |
| 8 | freeway | 100 |
| 9 | golfcourse | 100 |
| 10 | harbor | 100 |
| 11 | intersection | 100 |
| 12 | mediumresidential | 100 |
| 13 | mobilehomepark | 100 |
| 14 | overpass | 100 |
| 15 | parkinglot | 100 |
| 16 | river | 100 |
| 17 | runway | 100 |
| 18 | sparseresidential | 100 |
| 19 | storagetanks | 100 |
| 20 | tenniscourt | 100 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/WHU-RS19",
"csv_file_path": "/media/hdd/multi-class/WHU-RS19/train.csv"
}
train_dataset = WHURS19Dataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 1005
| Label | Count | |
|---|---|---|
| 0 | Airport | 55 |
| 1 | Beach | 50 |
| 2 | Bridge | 52 |
| 3 | Commercial | 56 |
| 4 | Desert | 50 |
| 5 | Farmland | 50 |
| 6 | Forest | 53 |
| 7 | Industrial | 53 |
| 8 | Meadow | 61 |
| 9 | Mountain | 50 |
| 10 | Park | 50 |
| 11 | Parking | 50 |
| 12 | Pond | 54 |
| 13 | Port | 53 |
| 14 | Residential | 54 |
| 15 | River | 56 |
| 16 | Viaduct | 58 |
| 17 | footballField | 50 |
| 18 | railwayStation | 50 |
train_dataset_config = {
"dir_path": "/media/hdd/multi-class/CLRS",
"csv_file_path": "/media/hdd/multi-class/CLRS/train.csv"
}
train_dataset = CLRSDataset(train_dataset_config)
print(f"Total number of images: {len(train_dataset)}")
fig = train_dataset.show_batch(15)
fig = train_dataset.data_distribution_barchart()
train_dataset.data_distribution_table()
Total number of images: 15000
| Label | Count | |
|---|---|---|
| 0 | airport | 600 |
| 1 | bare-land | 600 |
| 2 | beach | 600 |
| 3 | bridge | 600 |
| 4 | commercial | 600 |
| 5 | desert | 600 |
| 6 | farmland | 600 |
| 7 | forest | 600 |
| 8 | golf-course | 600 |
| 9 | highway | 600 |
| 10 | industrial | 600 |
| 11 | meadow | 600 |
| 12 | mountain | 600 |
| 13 | overpass | 600 |
| 14 | park | 600 |
| 15 | parking | 600 |
| 16 | playground | 600 |
| 17 | port | 600 |
| 18 | railway | 600 |
| 19 | railway-station | 600 |
| 20 | residential | 600 |
| 21 | river | 600 |
| 22 | runway | 600 |
| 23 | stadium | 600 |
| 24 | storage-tank | 600 |